Is Qwen3.6-35B-A3B-DFlash or gemma-3-270m-it smaller?

Qwen3.6-35B-A3B-DFlash is smaller at Q4_K_M: 0.22 GiB against 0.24 GiB.

Which uses less memory at long context?

gemma-3-270m-it — its KV cache at 32K context is 2.0x smaller, because of how its attention layers cache.

Model comparison

Qwen3.6-35B-A3B-DFlash vs gemma-3-270m-it

At Q4_K_M, Qwen3.6-35B-A3B-DFlash is the smaller download — 235,691,744 bytes against 253,115,168. At long context the gap widens: gemma-3-270m-it's KV cache at 32K is 2.0× smaller, which usually matters more than the difference in weights.

From the file· summed bytes, KV per layer

Side by side

	Qwen3.6-35B-A3B-DFlash	gemma-3-270m-it
Parameters	386M	268M
Architecture	dflash	gemma3
Layers	6	18
Native context	262,144	32,768
Mixture of experts	no	no
Quantizations published	18	39
Smallest quantization	0.14 GiB	0.17 GiB
Q4_K_M	0.22 GiB	0.24 GiB
Licence	apache-2.0	gemma

KV cache by context

the term that decides long-context viability

Context	Qwen3.6-35B-A3B-DFlash	gemma-3-270m-it	Ratio
4,096	0.09 GiB	0.03 GiB	3.56×
8,192	0.12 GiB	0.04 GiB	3.13×
16,384	0.15 GiB	0.06 GiB	2.44×
32,768	0.21 GiB	0.11 GiB	1.96×
65,536	0.34 GiB	0.20 GiB	1.67×
131,072	0.59 GiB	0.39 GiB	1.51×